Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3117 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3964. Min Range: -5.3964
Max Act: 5.3964. Min Act: -0.1700
Data Index: 170646 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3964. Min Range: -5.3964
Max Act: 5.1464. Min Act: -0.1700
Data Index: 537619 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3964. Min Range: -5.3964
Max Act: 5.0526. Min Act: -0.1700
Data Index: 8653219 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3964. Min Range: -5.3964
Max Act: 5.0214. Min Act: -0.1700
Data Index: 3230387 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3964. Min Range: -5.3964
Max Act: 5.0214. Min Act: -0.1700
Data Index: 5017534 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3964. Min Range: -5.3964
Max Act: 5.0214. Min Act: -0.1700
Data Index: 8624089 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3964. Min Range: -5.3964
Max Act: 5.0214. Min Act: -0.1700
Data Index: 356350 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3964. Min Range: -5.3964
Max Act: 4.9901. Min Act: -0.1700
Data Index: 21353 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3964. Min Range: -5.3964
Max Act: 4.9589. Min Act: -0.1700
Data Index: 7921919 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3964. Min Range: -5.3964
Max Act: 4.9901. Min Act: -0.1700
Data Index: 2300335 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3964. Min Range: -5.3964
Max Act: 4.9589. Min Act: -0.1700
Data Index: 6159313 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3964. Min Range: -5.3964
Max Act: 4.9589. Min Act: -0.1700
Data Index: 6310638 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3964. Min Range: -5.3964
Max Act: 4.9589. Min Act: -0.1700
Data Index: 8177649 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3964. Min Range: -5.3964
Max Act: 4.9589. Min Act: -0.1700
Data Index: 3083567 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3964. Min Range: -5.3964
Max Act: 4.9589. Min Act: -0.1700
Data Index: 8638069 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3964. Min Range: -5.3964
Max Act: 4.9276. Min Act: -0.1700
Data Index: 1581864 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3964. Min Range: -5.3964
Max Act: 4.9276. Min Act: -0.1700
Data Index: 642665 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3964. Min Range: -5.3964
Max Act: 4.8651. Min Act: -0.1700
Data Index: 7629099 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3964. Min Range: -5.3964
Max Act: 4.9276. Min Act: -0.1700
Data Index: 3350033 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3964. Min Range: -5.3964
Max Act: 4.8964. Min Act: -0.1700
Data Index: 5728391 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19